Gestura-Edu

A fun, inclusive platform to learn Indian Sign Language — from basic signs to full sentences, with live practice & playground to build real-world ISL skills.

Comment

Inspiration

We initially started this project with the aim of learning machine learning and deep learning techniques. Along the way, we discovered the power of landmark detection and realized that direct feature operations were possible — eliminating the need for large training datasets. This discovery inspired us to build a real-time sign language recognition system.

What it does

Gestura-Edu is an accessible educational platform to learn Indian Sign Language (ISL). It allows users to explore beginner and intermediate signs, practice live with a camera, and test sentence comprehension through an interactive playground — making ISL learning inclusive and engaging.

How we built it

We used MediaPipe to capture and normalize hand landmarks, and applied FastDTW for efficient gesture matching without any deep learning models. We designed a backend with multi-user support and a cross-platform web frontend. For this hackathon, we transformed the system into an educational tool, adding modes for Beginner and Intermediate Signs, as well as Playground to learn Sentence Formation in Sign Language!

Challenges we ran into

  • Designing lightweight, real-time recognition without CNN/LSTM models.
  • Normalizing gestures across varying angles and hand sizes.
  • Creating an intuitive and accessible educational interface.
  • Ensuring community relevance by incorporating real feedback from schools and local users.

Accomplishments that we're proud of

  • Built a working prototype that detects dynamic signs without model training.
  • Received positive feedback from the academic community.
  • Successfully tested the platform with local schools and communities.
  • Developed an inclusive learning tool aligned with UN SDG goals.

What we learned

We learned that impactful solutions don’t always require heavy AI models — creative use of existing tools can achieve powerful results. We also discovered the importance of community feedback in shaping educational tools and the need for accessible tech in underserved spaces.

What's next for Gestura-Edu

We aim to expand Gestura-Edu to include ASL and other global sign languages, form collaborations with educators and NGOs, and improve gesture accuracy, especially under angle variation. We also plan to increase outreach, bringing this tool to more schools, communities, and public spaces worldwide.

Built With

Share this project:

Updates